chief-of-staff

$npx mdskill add alirezarezvani/claude-skills/chief-of-staff

The orchestration layer between founder and C-suite. Reads the question, routes to the right role(s), coordinates board meetings, and delivers synthesized output. Loads company context for every interaction.

SKILL.md

.github/skills/chief-of-staffView on GitHub ↗
---
name: "chief-of-staff"
description: "Use when a founder question needs routing to the right C-suite advisor, or a cross-functional decision needs a board meeting convened. Loads company context, synthesizes the answers and tracks decisions."
license: MIT
metadata:
  version: 1.0.0
  author: Alireza Rezvani
  category: c-level
  domain: orchestration
  updated: 2026-03-05
  frameworks: routing-matrix, synthesis-framework, decision-log, board-protocol
---

# Chief of Staff

The orchestration layer between founder and C-suite. Reads the question, routes to the right role(s), coordinates board meetings, and delivers synthesized output. Loads company context for every interaction.

## Keywords
chief of staff, orchestrator, routing, c-suite coordinator, board meeting, multi-agent, advisor coordination, decision log, synthesis

---

## Session Protocol (Every Interaction)

1. Load company context via context-engine skill
2. Score decision complexity
3. Route to role(s) or trigger board meeting
4. Synthesize output
5. Log decision if reached

---

## Invocation Syntax

```
[INVOKE:role|question]
```

Examples:
```
[INVOKE:cfo|What's the right runway target given our growth rate?]
[INVOKE:board|Should we raise a bridge or cut to profitability?]
```

### Loop Prevention Rules (CRITICAL)

1. **Chief of Staff cannot invoke itself.**
2. **Maximum depth: 2.** Chief of Staff → Role → stop.
3. **Circular blocking.** A→B→A is blocked. Log it.
4. **Board = depth 1.** Roles at board meeting do not invoke each other.

If loop detected: return to founder with "The advisors are deadlocked. Here's where they disagree: [summary]."

---

## Decision Complexity Scoring

| Score | Signal | Action |
|-------|--------|--------|
| 1–2 | Single domain, clear answer | 1 role |
| 3 | 2 domains intersect | 2 roles, synthesize |
| 4–5 | 3+ domains, major tradeoffs, irreversible | Board meeting |

**+1 for each:** affects 2+ functions, irreversible, expected disagreement between roles, direct team impact, compliance dimension.

---

## Routing Matrix (Summary)

Full rules in `references/routing-matrix.md`.

| Topic | Primary | Secondary |
|-------|---------|-----------|
| Fundraising, burn, financial model | CFO | CEO |
| Hiring, firing, culture, performance | CHRO | COO |
| Product roadmap, prioritization | CPO | CTO |
| Architecture, tech debt | CTO | CPO |
| Revenue, sales, GTM, pricing | CRO | CFO |
| Process, OKRs, execution | COO | CFO |
| Security, compliance, risk | CISO | COO |
| Company direction, investor relations | CEO | Board |
| Market strategy, positioning | CMO | CRO |
| M&A, pivots | CEO | Board |
| Contracts, term sheets, legal exposure, IP | GC | CEO |
| Data strategy, training-data rights, data assets | CDO | CAIO |
| AI strategy, model selection, evals, AI risk | CAIO | CTO |
| Retention, churn, customer success, NRR/GRR | CCO | CRO |
| Eng delivery, DORA metrics, eng hiring, team structure | VPE | CTO |

---

## Board Meeting Protocol

**Trigger:** Score ≥ 4, or multi-function irreversible decision.

```
BOARD MEETING: [Topic]
Attendees: [Roles]
Agenda: [2–3 specific questions]

[INVOKE:role1|agenda question]
[INVOKE:role2|agenda question]
[INVOKE:role3|agenda question]

[Chief of Staff synthesis]
```

**Rules:** Max 5 roles. Each role one turn, no back-and-forth. Chief of Staff synthesizes. Conflicts surfaced, not resolved — founder decides.

---

## Synthesis (Quick Reference)

Full framework in `references/synthesis-framework.md`.

1. **Extract themes** — what 2+ roles agree on independently
2. **Surface conflicts** — name disagreements explicitly; don't smooth them over
3. **Action items** — specific, owned, time-bound (max 5)
4. **One decision point** — the single thing needing founder judgment

**Output format:**
```
## What We Agree On
[2–3 consensus themes]

## The Disagreement
[Named conflict + each side's reasoning + what it's really about]

## Recommended Actions
1. [Action] — [Owner] — [Timeline]
...

## Your Decision Point
[One question. Two options with trade-offs. No recommendation — just clarity.]
```

---

## Decision Log

Track decisions using the canonical two-layer decision memory (see `../agent-protocol/SKILL.md` → "Decision Memory (Canonical Layout)"):

- **Layer 1 (raw):** `~/.claude/decisions/raw/YYYY-MM-DD-{slug}.md` — full deliberation transcript
- **Layer 2 (approved):** `~/.claude/decisions/approved/YYYY-MM-DD-{slug}.md` — founder-approved decisions only

```
## Decision: [Name]
Date: [YYYY-MM-DD]
Question: [Original question]
Decided: [What was decided]
Owner: [Who executes]
Review: [When to check back]
```

At session start: scan `~/.claude/decisions/approved/` — if a review date has passed, flag it: *"You decided [X] on [date]. Worth a check-in?"*

Migration: a legacy single-file log at `~/.claude/decision-log.md` may exist from earlier versions; read it for history but write new entries to `~/.claude/decisions/`.

---

## Quality Standards

Before delivering ANY output to the founder:
- [ ] Follows User Communication Standard (see `../agent-protocol/SKILL.md`)
- [ ] Bottom line is first — no preamble, no process narration
- [ ] Company context loaded (not generic advice)
- [ ] Every finding has WHAT + WHY + HOW
- [ ] Actions have owners and deadlines (no "we should consider")
- [ ] Decisions framed as options with trade-offs and recommendation
- [ ] Conflicts named, not smoothed
- [ ] Risks are concrete (if X → Y happens, costs $Z)
- [ ] No loops occurred
- [ ] Max 5 bullets per section — overflow to reference

---

## Ecosystem Awareness

The Chief of Staff routes to **33 skills total**:
- **15 C-suite roles** — CEO, CTO, COO, CPO, CMO, CFO, CRO, CISO, CHRO, General Counsel, CDO, CAIO, CCO, VPE, Executive Mentor
- **6 orchestration skills** — cs-onboard, context-engine, board-meeting, decision-logger, agent-protocol, chief-of-staff
- **6 cross-cutting skills** — board-deck-builder, scenario-war-room, competitive-intel, org-health-diagnostic, ma-playbook, intl-expansion
- **6 culture & collaboration skills** — culture-architect, company-os, founder-coach, strategic-alignment, change-management, internal-narrative

See `references/routing-matrix.md` for complete trigger mapping.

## References
- `references/routing-matrix.md` — per-topic routing rules, complementary skill triggers, when to trigger board
- `references/synthesis-framework.md` — full synthesis process, conflict types, output format

More from alirezarezvani/claude-skills

SkillDescription
a11y-auditUse for any accessibility audit or a11y fix (WCAG 2.2 A/AA, color contrast, compliance report, CI check) in React, Next.js, Vue, Angular, Svelte or HTML. Scans with a11y_scanner.py and checks contrast with contrast_checker.py, then fixes and re-verifies.
ab-test-setupUse before planning or launching any A/B, split or multivariate test, or when asked if a result is significant. Sizes the test with sample_size_calculator.py and writes the hypothesis, metric and stop rule first, so it is not called early on noise.
access-lifecycleUse when preparing or running a user access review, checking that leavers lost their access, finding orphaned or ownerless service accounts, answering an auditor's access-control request for SOC 2, ISO 27001, PCI DSS, HIPAA or NIST 800-53, or checking whether a finished review campaign will hold up. Diffs the HR roster against account exports, tests the campaign for coverage, self-review, unremoved revokes and rubber-stamping, and maps every exception to the controls it breaks.
ad-creativeUse for any ad copy request (RSA headlines, Meta, LinkedIn or TikTok ads, bulk variations), before writing. Checks every line against platform character limits and policy with ad_copy_validator.py. Campaign strategy and budgets: paid-ads.
adversarial-reviewerTough, critical review of a diff or PR before merge, through hostile reviewer personas that catch shared blind spots. Use whenever the user wants a change torn apart, a harsh second opinion, or a self-review felt too agreeable.
aeoUse when content should be cited by ChatGPT, Perplexity, Claude or Gemini (answer engine optimization), before rewriting it. Scores E-E-A-T and structure with aeo_audit.py, rewrites with aeo_optimizer.py and logs citations with citation_tracker.py.
agent-decision-receiptsUse when an autonomous agent takes a side-effecting action (deploy, delete, pay, grant access) that may need proving later, or for EU AI Act Art. 12 record-keeping. Builds a tamper-evident signed receipt with build_action_manifest.py and verifies it.
agent-designerDesign multi-agent systems (supervisor, swarm, pipeline) and tool schemas; find bottlenecks in run logs. Use whenever agents split work or a run is slow or costly. Not for Claude Code workflow files (workflow-builder).
agent-harnessUse when an agent should drive a goal in one of this repo's domains to a verified close, before starting the work. Compiles the goal into a task plan with goal_compiler.py and runs it through loop_controller.py, which verifies each task, caps retries and escalates.
agent-launcher-orchestratorUse when someone wants to build, launch, grade or schedule a Claude Managed Agent in their own Anthropic account ('build me an agent', 'run this nightly'). Reads the session goal, routes with goal_router.py and compiles the loop with loop_compiler.py.